mlsanityData to 7 Oct 2026

Solving Inverse Problems using Diffusion with Iterative Colored Renoising

arXiv 2501.17468 ↗First posted 29 Jan 2025cs.CVcited by 1

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Imaging inverse problems can be solved in an unsupervised manner using pre-trained diffusion models, but doing so requires approximating the gradient of the measurement-conditional score function in the diffusion reverse process. We show that the approximations produced by existing methods are relatively poor, especially early in the reverse process, and so we propose a new approach that iteratively reestimates and "renoises" the estimate several times per diffusion step. This iterative approach, which we call Fast Iterative REnoising (FIRE), injects colored noise that is shaped to ensure that the pre-trained diffusion model always sees white noise, in accordance with how it was trained. We then embed FIRE into the DDIM reverse process and show that the resulting "DDfire" offers state-of-the-art accuracy and runtime on several linear inverse problems, as well as phase retrieval. Our implementation is at https://github.com/matt-bendel/DDfire

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 30 of its 51 references that are in the map. First posted on arXiv 29 Jan 2025.

Builds on

30 of 51 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024A Survey on Diffusion Models for Inverse Problems30 Sep
  2. 2024Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing1 Jul
  3. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors29 May
  4. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction25 Mar
  5. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  6. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models7 May
  7. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems10 Mar
  8. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  9. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  10. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  10. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  11. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  12. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
8 more
  1. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  2. 2023The probability flow ODE is provably fastcited by 145
  3. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 102
  4. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 96
  5. 2023Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inferencecited by 41
  6. 2013Phase Retrieval from Coded Diffraction Patternscited by 26
  7. 2023Generative Plug and Play: Posterior Sampling for Inverse Problemscited by 24
  8. 2024Plug-and-Play image restoration with Stochastic deNOising REgularizationcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion models for inverse problems
  2. 2023Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
  3. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
  4. 2024Fast Samplers for Inverse Problems in Iterative Refinement Models
  5. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
  6. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
  7. 2024Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization
  8. 2022Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems